Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Warfare
    -0.08
     WIN
    -0.07
    кол
    -0.07
     skins
    -0.07
    �
    -0.07
    hunter
    -0.07
     cloud
    -0.07
     fetal
    -0.06
    ﻤ
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    liğinde
    0.06
    _ctr
    0.06
    audi
    0.06
     zengin
    0.06
    .UN
    0.06
    sian
    0.06
     singled
    0.06
    луги
    0.06
    +↵↵
    0.06
    _change
    0.05
    Act Density 0.134%

    No Known Activations